nWave-ai/nWave

AI agents that guide you from idea to working code, with you in control at every step.

What it solves

nWave is an AI-driven development framework that prevents the "where do I start?" confusion by guiding developers from an initial idea to working code through a structured, multi-stage process. It ensures high software quality by enforcing engineering disciplines like Test-Driven Development (TDD) and peer reviews, preventing AI agents from running unsupervised end-to-end.

How it works

nWave operates as a plugin for Claude Code (and supports Codex CLI and OpenCode). It breaks feature delivery into seven "waves" (Discover, Diverge, Discuss, Design, DevOps, Distill, and Deliver). Specialized agents handle each wave, producing artifacts that the human developer must review and approve before the process can proceed to the next stage.

To maintain quality, nWave uses a Delivery Enforcement System (DES) that monitors tool invocations to ensure TDD phases (e.g., RED $\rightarrow$ GREEN $\rightarrow$ COMMIT) are followed and protects files from accidental edits during active delivery sessions.

Who it’s for

It is designed for developers who want to use AI agents to build software while maintaining strict control over the architecture, requirements, and code quality through human-in-the-loop validation.

Highlights

  • Structured Workflow: A seven-wave process that routes users based on context (e.g., greenfield projects vs. bug fixes).
  • Human-in-the-Loop: Requires human approval at every gate to prevent unsupervised AI execution.
  • Quality Enforcement: Integrated DES for TDD validation and audit logging.
  • Adjustable Rigor: Configurable quality profiles (lean, standard, thorough, exhaustive) to allow developers to trade off token cost for depth of review and testing.
  • Agent Ecosystem: A library of 40 specialized agents, including product discoverers, system designers, and software crafters.

Related

  • Project
    shinpr/claude-code-workflows

    A set of structured development workflows and plugins for Claude Code that ensure AI-generated code stays within scope and is verified against agreed-upon design documents.

  • Project
    pedrohcgs/claude-code-my-workflow

    A ready-to-fork foundation for AI-assisted academic work that uses Claude Code to automate the planning, creation, and verification of research papers, slides, and data analysis.

  • Project
    Owl-Listener/designer-skills

    A set of Claude Code/Gemini‑CLI plugins that turn design knowledge into machine‑readable skills and ready‑to‑run commands, letting AI agents execute full design workflows (research, strategy, UI, interaction, systems, ops, critique) directly from the assistant.

  • Project
    umputun/cc-thingz

    A marketplace of Claude Code plugins that add brainstorming, PR review, planning, release automation, thinking aids, skill‑evaluation hooks, and workflow helpers. Install via `/plugin marketplace add umputun/cc-thingz` and pick the plugins you need.

  • Project
    dongbeixiaohuo/writing-agent

    A multi-agent AI writing assistant that turns article creation into an interactive, reviewable process: a writing director, researcher, main writer, editors, reader simulators, and fact-checkers collaborate with you stage by stage. Ships as a Windows desktop app (RC) and as a Claude Code Skill, with 99 model presets, optional web search for fact-checking, local versioned storage, and full run logs.